Abstract
Research on language acquisition for academic purposes is not extensive. In this work, we propose to build a system for recognizing teaching activities from automatic transcriptions of classroom audio and video recordings centered on the professor’s discourse. To this end, we identified the main teaching activities that cover the nature of the lecturer discourse when giving a course e.g. ‘theoretical explanation’, real-world practical example’, interaction lecturer-student’, ‘course-related asides’, etc. We labeled a dataset of lecture transcriptions from a repository with an approximate length of 50 h and we build a classifier by fine-tuning the XLM-RoBERTa model with a classification head on top of it. The results will show that our proposal is a promising step ahead towards recognition of discourse activities in academic contexts.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
MLLP transcriptions. https://ttp.mllp.upv.es/index.php?page=faq.
References
Biber, D.: Dimensions of Register Variation: A Cross-linguistic Comparison. Cambridge University Press, New York (1995)
Biewald, L.: Experiment tracking with weights and biases (2020). https://www.wandb.com/. software available from wandb.com
Conneau, A., et al.: Unsupervised Cross-lingual Representation Learning at Scale (2020)
Csomay, E.: Academic lectures: an interface of an oral/literate continuum. NovELTy 7(3), 30–48 (2000)
Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. CoRR abs/1810.04805 (2018). http://arxiv.org/abs/1810.04805
Fortanet-Gómez, I.: Honoris Causa speeches: an approach to structure. Discourse Stud. 7(1), 31–51 (2005)
Fortanet-Gómez, I., Bellés-Fortuño, B.: Spoken academic discourse: an approach to research on lectures. Revista española de lingüística aplicada 1(8), 161–178 (2005)
Ganek, H., Eriks-Brophy, A.: Language ENvironment analysis (LENA) system investigation of day long recordings in children: a literature review. J. Commun. Disord. 72, 77–85 (2018)
LENA Research Foundation: The LENA research foundation (2014). http://www.lenafoundation.org/
Liu, Y., et al.: RoBERTa: A Robustly Optimized BERT Pretraining Approach (2019)
Malavska, V.: Genre of an academic lecture. Int. J. Lang. Lit. Cult. Educ. 3(2), 56–84 (2016)
Owens, M.T., et al.: Classroom sound can be used to classify teaching practices in college science courses. Proc. Nat. Acad. Sci. 114(12), 3085–3090 (2017). https://doi.org/10.1073/pnas.1618693114
Wang, Z., Pan, X., Miller, K.F., Cortina, K.S.: Automatic classification of activities in classroom discourse. Comput. Educ. 78, 115–123 (2014)
Wolf, T., et al: Huggingface’s transformers: state-of-the-art natural language processing. CoRR abs/1910.03771 (2019)
Young, L.: University Lectures - Macro-structure and Micro-features, pp. 159–176. Cambridge University Press, Cambridge Applied Linguistics (1995). https://doi.org/10.1017/CBO9781139524612.013
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Diosdado, D., Romero, A., Onaindia, E. (2021). Recognition of Teaching Activities from University Lecture Transcriptions. In: Alba, E., et al. Advances in Artificial Intelligence. CAEPIA 2021. Lecture Notes in Computer Science(), vol 12882. Springer, Cham. https://doi.org/10.1007/978-3-030-85713-4_22
Download citation
DOI: https://doi.org/10.1007/978-3-030-85713-4_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-85712-7
Online ISBN: 978-3-030-85713-4
eBook Packages: Computer ScienceComputer Science (R0)